<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bagherzadeh-bergler-2021-competing-independent">
    <titleInfo>
        <title>Competing Independent Modules for Knowledge Integration and Optimization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Parsa</namePart>
        <namePart type="family">Bagherzadeh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sabine</namePart>
        <namePart type="family">Bergler</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marie-Francine</namePart>
            <namePart type="family">Moens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Xuanjing</namePart>
            <namePart type="family">Huang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lucia</namePart>
            <namePart type="family">Specia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Scott</namePart>
            <namePart type="given">Wen-tau</namePart>
            <namePart type="family">Yih</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper presents a neural framework of untied independent modules, used here for integrating off the shelf knowledge sources such as language models, lexica, POS information, and dependency relations. Each knowledge source is implemented as an independent component that can interact and share information with other knowledge sources. We report proof of concept experiments for several standard sentiment analysis tasks and show that the knowledge sources interoperate effectively without interference. As a second use-case, we show that the proposed framework is suitable for optimizing BERT-like language models even without the help of external knowledge sources. We cast each Transformer layer as a separate module and demonstrate performance improvements from this explicit integration of the different information encoded at the different Transformer layers .</abstract>
    <identifier type="citekey">bagherzadeh-bergler-2021-competing-independent</identifier>
    <identifier type="doi">10.18653/v1/2021.findings-emnlp.376</identifier>
    <location>
        <url>https://aclanthology.org/2021.findings-emnlp.376/</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>4416</start>
            <end>4425</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Competing Independent Modules for Knowledge Integration and Optimization
%A Bagherzadeh, Parsa
%A Bergler, Sabine
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F bagherzadeh-bergler-2021-competing-independent
%X This paper presents a neural framework of untied independent modules, used here for integrating off the shelf knowledge sources such as language models, lexica, POS information, and dependency relations. Each knowledge source is implemented as an independent component that can interact and share information with other knowledge sources. We report proof of concept experiments for several standard sentiment analysis tasks and show that the knowledge sources interoperate effectively without interference. As a second use-case, we show that the proposed framework is suitable for optimizing BERT-like language models even without the help of external knowledge sources. We cast each Transformer layer as a separate module and demonstrate performance improvements from this explicit integration of the different information encoded at the different Transformer layers .
%R 10.18653/v1/2021.findings-emnlp.376
%U https://aclanthology.org/2021.findings-emnlp.376/
%U https://doi.org/10.18653/v1/2021.findings-emnlp.376
%P 4416-4425

Markdown (Informal)

[Competing Independent Modules for Knowledge Integration and Optimization](https://aclanthology.org/2021.findings-emnlp.376/) (Bagherzadeh & Bergler, Findings 2021)

• Competing Independent Modules for Knowledge Integration and Optimization (Bagherzadeh & Bergler, Findings 2021)

ACL

• Parsa Bagherzadeh and Sabine Bergler. 2021. Competing Independent Modules for Knowledge Integration and Optimization. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4416–4425, Punta Cana, Dominican Republic. Association for Computational Linguistics.